Maintainer of this skill?
Automated security scan — not a certification.
by 7df-lab
A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills.
# Add to your Claude Code skills
git clone https://github.com/7df-lab/devoGuides for using ai agents skills like devo.
Last scanned: 6/27/2026
{
"issues": [
{
"file": "README.md",
"line": 148,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://raw.githubusercontent.com/7df-lab/devo/main/install.sh | sh\"",
"severity": "low"
}
],
"status": "PASSED",
"scannedAt": "2026-06-27T06:52:11.481Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how devo compares with popular alternatives.
devo is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by 7df-lab. A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills. It has 345 GitHub stars.
Yes. devo passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/7df-lab/devo" and add it to your Claude Code skills directory (see the Installation section above).
devo is primarily written in Rust. It is open-source under 7df-lab on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh devo against similar tools.
No comments yet. Be the first to share your thoughts!
From $49 · 30 days · terms & refunds
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Automated security scan — not a certification.
Devo tackles multi-step work with a persistent Python workspace, child agents, and your choice of model provider. Use the Desktop app or terminal TUI/CLI, powered by a local Rust runtime.
English · 简体中文 · 繁體中文 · 日本語 · Русский
| Agent | Main emphasis | Models |
|---|---|---|
| Devo | Programmable, recursive execution for coding and other multi-step tasks. | Compatible cloud providers, local endpoints, and private gateways. |
| Claude Code | Claude-centered development across terminal, IDE, desktop, and web. | Claude through Anthropic or supported cloud providers. |
| Codex | OpenAI's coding agent across terminal, IDE, app, and cloud. | OpenAI models by default; the CLI also supports custom and local providers. |
Devo's ipython tool keeps variables and intermediate results across calls.
The agent can filter large outputs in Python, reuse earlier work, and delegate
independent subtasks to child agents with their own sessions and Python state.
MCP, skills, permissions, and resumable sessions round out the workflow.
Children can independently select a configured model and reasoning level:
models = await rlm.find_models(limit=100)
chosen = next((m for m in models if "high" in m.thinking_levels), None)
if chosen is not None:
reviewer = await rlm.spawn(
"Review the current diff.", name="reviewer",
model=chosen.selector, thinking="high",
)
Omitted options inherit the immediate parent. Invalid selections fail without fallback. Discovery reflects configuration, not live health or credits. See the child model API.
Desktop: Download the package for your OS and architecture from GitHub Releases, then connect a model provider in the setup flow.
Terminal — Linux / macOS:
curl -fsSL https://raw.githubusercontent.com/7df-lab/devo/main/install.sh | sh
Terminal — Windows PowerShell:
irm 'https://raw.githubusercontent.com/7df-lab/devo/main/install.ps1' | iex
Start in your workspace; first launch opens provider setup:
cd /path/to/your/workspace
devo
Resume with devo resume <session-id>; upgrade with devo upgrade.
Terminal bundles include Node.js and Python. On Windows, install
Git for Windows for shell commands and approve
the one-time sandbox setup prompt.
Shell and terminal execution follow the configured sandbox profile; there is no global sandbox-disable switch. Python kernels are trusted user-privileged processes, not OS-isolated environments. See the execution boundary. Permission-picker UI flags and new-session permission defaults are separate settings; removing the global switch does not change them.
Connect endpoints using OpenAI-compatible Chat Completions, OpenAI-compatible
Responses, or Anthropic Messages APIs. The bundled catalog includes
DeepSeek, Qwen, Kimi, GLM, and MiniMax. Use /model to switch models or
devo onboard to revisit provider setup.
For manual configuration, credentials, MCP, offline installation, and release mirrors, see the user guide.
Devo is pre-1.0; APIs and configuration may change. MIT License.